© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21108
    Prev
    Next
    INDEX
    Explanations

    his or her possessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¥ĩçļĦ
    -0.06
    zem
    -0.06
     reve
    -0.06
    ÙĪÛĮÙĦ
    -0.06
     dew
    -0.05
    allah
    -0.05
    мееÑĤÑģÑı
    -0.05
     ê´Ģ리
    -0.05
    å±ħæ°ijçļĦ
    -0.05
    otre
    -0.05
    POSITIVE LOGITS
    uments
    0.05
     orienta
    0.05
     Dere
    0.05
     exporta
    0.05
    åıĤèĢĥçŃĶæ¡Ī
    0.05
     espa
    0.05
    ä»İä¸ļèµĦæł¼
    0.05
    ieg
    0.05
    æѤåīį
    0.05
    iggio
    0.05
    Activations Density 0.044%

    No Known Activations